ClawHub
Back to skill

Security audit

alias

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only academic writing template skill with no executable code, persistence, credential handling, or hidden data access.

Install this if you specifically want Tikrit University CS/Math graduation research formatting. For general academic writing, expect it to impose that institution-specific structure, bilingual abstracts, Arabic front matter, and .docx-oriented conventions unless you override them in your prompt.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger definition is very broad and instructs the system to "always use this skill" for many generic writing-related requests, including partial tasks like abstracts or chapter sections. This can cause the skill to activate outside its intended niche, overriding more appropriate skills or user intent and leading to unwanted generation of full academic content, which is a scope-control and policy-enforcement risk.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The skill hard-codes bilingual and Arabic-only sections as mandatory without checking whether the user wants or is authorized to receive that format. While not a classic security exploit, this can force unexpected content generation, reduce user control, and increase the chance of producing inappropriate or non-compliant output for users outside the intended institutional context.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
The title and introductory text state that the abstract phrases are specifically for the Arabic 'الخلاصة' section and that this section always appears at the end of the document. This prescribes a specific language/locale convention without indicating that users may choose another language or that the constraint is optional or context-specific.

Static analysis

No suspicious patterns detected.